Updated Datasets (#102)

Deep-Learning-Profiling-Tools · Apr 20, 2024 · bc85a6d · bc85a6d
1 parent 8833b4f
commit bc85a6d
Show file tree

Hide file tree

Showing 36 changed files with 58 additions and 372 deletions.
diff --git a/README.md b/README.md
@@ -1,9 +1,9 @@
 # FASTEN: A Library of *Fast Segment* Operators
 
 ## Introduction
-FASTEN is a library aimed at speeding up Heterogeneous Graph Neural Network (HGNN) workloads.   
+FASTEN is a library aimed at speeding up Heterogeneous Graph Neural Network (HGNN) workloads.
 The current version of FASTEN focuses on improving segmented matrix multiplication, a critical operator in HGNNs.
-Fasten implements a simple interface, making it easy to integrate with existing graph library PyG with minimal changes.  
+Fasten implements a simple interface, making it easy to integrate with existing graph library PyG with minimal changes.
 
 ## Installation
 
@@ -22,7 +22,7 @@ pip install .
 ```
 
 ## Examples
-FASTEN's segment matrix multiplication operator has been integrated with various HGNN architecture such as *RGCN*, *HGT*, *RGAT* in PyG.  
+FASTEN's segment matrix multiplication operator has been integrated with various HGNN architecture such as *RGCN*, *HGT*, *RGAT* in PyG.
 Examples on how to run the examples can be found below:
 
 ### GNN Examples

diff --git a/test/datasets_csv/ACM.csv b/test/datasets_csv/ACM.csv
@@ -0,0 +1,5 @@
+Start,End
+0,5343
+5343,15292
+15292,18317
+18317,273936
diff --git a/test/datasets_csv/ACM1.csv b/test/datasets_csv/ACM1.csv
diff --git a/test/datasets_csv/ACM2.csv b/test/datasets_csv/ACM2.csv
diff --git a/test/datasets_csv/AMiner1.csv b/test/datasets_csv/AMiner1.csv
diff --git a/test/datasets_csv/AMiner2.csv b/test/datasets_csv/AMiner2.csv
diff --git a/test/datasets_csv/AmazonBook1.csv b/test/datasets_csv/AmazonBook1.csv
diff --git a/test/datasets_csv/AmazonBook2.csv b/test/datasets_csv/AmazonBook2.csv
diff --git a/test/datasets_csv/DBLP.csv b/test/datasets_csv/DBLP.csv
@@ -1,97 +1,4 @@
-Start,End
-0,4057
-4057,18385
-18385,32713
-32713,47041
-47041,54764
-54764,54784
-54784,58841
-58841,73169
-73169,87497
-87497,101825
-101825,109548
-109548,109568
-109568,113625
-113625,127953
-127953,142281
-142281,156609
-156609,164332
-164332,164352
-164352,168409
-168409,182737
-182737,197065
-197065,211393
-211393,219116
-219116,219136
-219136,223193
-223193,237521
-237521,251849
-251849,266177
-266177,273900
-273900,273920
-273920,277977
-277977,292305
-292305,306633
-306633,320961
-320961,328684
-328684,328704
-328704,332761
-332761,347089
-347089,361417
-361417,375745
-375745,383468
-383468,383488
-383488,387545
-387545,401873
-401873,416201
-416201,430529
-430529,438252
-438252,438272
-438272,442329
-442329,456657
-456657,470985
-470985,485313
-485313,493036
-493036,493056
-493056,497113
-497113,511441
-511441,525769
-525769,540097
-540097,547820
-547820,547840
-547840,551897
-551897,566225
-566225,580553
-580553,594881
-594881,602604
-602604,602624
-602624,606681
-606681,621009
-621009,635337
-635337,649665
-649665,657388
-657388,657408
-657408,661465
-661465,675793
-675793,690121
-690121,704449
-704449,712172
-712172,712192
-712192,716249
-716249,730577
-730577,744905
-744905,759233
-759233,766956
-766956,766976
-766976,771033
-771033,785361
-785361,799689
-799689,814017
-814017,821740
-821740,821760
-821760,825817
-825817,840145
-840145,854473
-854473,868801
-868801,876524
-876524,876544
+Start,End
+0,19645
+19645,105455
+105455,119783
diff --git a/test/datasets_csv/DBLP1.csv b/test/datasets_csv/DBLP1.csv
diff --git a/test/datasets_csv/DBLP2.csv b/test/datasets_csv/DBLP2.csv
diff --git a/test/datasets_csv/Freebase.csv b/test/datasets_csv/Freebase.csv
@@ -0,0 +1,37 @@
+Start,End
+0,202674
+202674,240973
+240973,247588
+247588,274509
+274509,296409
+296409,384247
+384247,415733
+415733,427024
+427024,710694
+710694,719669
+719669,762584
+762584,769347
+769347,770637
+770637,771293
+771293,806880
+806880,824484
+824484,835432
+835432,850282
+850282,873095
+873095,888229
+888229,890444
+890444,895822
+895822,917121
+917121,964938
+964938,978066
+978066,988768
+988768,989327
+989327,992023
+992023,993124
+993124,994197
+994197,1012822
+1012822,1021219
+1021219,1045983
+1045983,1046593
+1046593,1053240
+1053240,1057688
diff --git a/test/datasets_csv/Freebase1.csv b/test/datasets_csv/Freebase1.csv
diff --git a/test/datasets_csv/Freebase2.csv b/test/datasets_csv/Freebase2.csv
diff --git a/test/datasets_csv/IGMCD_Douban1.csv b/test/datasets_csv/IGMCD_Douban1.csv
diff --git a/test/datasets_csv/IGMCD_Douban2.csv b/test/datasets_csv/IGMCD_Douban2.csv
diff --git a/test/datasets_csv/IGMCD_Flixster1.csv b/test/datasets_csv/IGMCD_Flixster1.csv
diff --git a/test/datasets_csv/IGMCD_Flixster2.csv b/test/datasets_csv/IGMCD_Flixster2.csv
diff --git a/test/datasets_csv/IGMCD_YahooMusic1.csv b/test/datasets_csv/IGMCD_YahooMusic1.csv
diff --git a/test/datasets_csv/IGMCD_YahooMusic2.csv b/test/datasets_csv/IGMCD_YahooMusic2.csv
diff --git a/test/datasets_csv/IMDB.csv b/test/datasets_csv/IMDB.csv
@@ -0,0 +1,4 @@
+Start,End
+0,4932
+4932,19711
+19711,43321
diff --git a/test/datasets_csv/IMDB1.csv b/test/datasets_csv/IMDB1.csv
diff --git a/test/datasets_csv/IMDB2.csv b/test/datasets_csv/IMDB2.csv
diff --git a/test/datasets_csv/LastFM1.csv b/test/datasets_csv/LastFM1.csv
diff --git a/test/datasets_csv/LastFM2.csv b/test/datasets_csv/LastFM2.csv
diff --git a/test/datasets_csv/MovieLens1.csv b/test/datasets_csv/MovieLens1.csv
diff --git a/test/datasets_csv/MovieLens1M1.csv b/test/datasets_csv/MovieLens1M1.csv